arabluatex_fullvoc.lua 38 KB

12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016
  1. --[[
  2. This file is part of the `arabluatex' package
  3. ArabLuaTeX -- Processing ArabTeX notation under LuaLaTeX
  4. Copyright (C) 2016--2018 Robert Alessi
  5. Please send error reports and suggestions for improvements to Robert
  6. Alessi <alessi@robertalessi.net>
  7. This program is free software: you can redistribute it and/or modify
  8. it under the terms of the GNU General Public License as published by
  9. the Free Software Foundation, either version 3 of the License, or
  10. (at your option) any later version.
  11. This program is distributed in the hope that it will be useful, but
  12. WITHOUT ANY WARRANTY; without even the implied warranty of
  13. MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
  14. General Public License for more details.
  15. You should have received a copy of the GNU General Public License
  16. along with this program. If not, see
  17. <http://www.gnu.org/licenses/>.
  18. --]]
  19. hamzafv = {
  20. -- next line for ʾiʿrāb hyphen
  21. {a="(')(%-)([uaiUAI])", b="%1%3"},
  22. -- next lines for ʾalif alone
  23. {a="(%.A)([uai]?)l%-(%^n)", b="ا%2ل%3"}, --additional (^n is lunar)
  24. {a="([%(%[%|%<%s%-O])(%.A)([uai]?)l%-(%^n)", b="%1ا%3%4"}, --additional (^n is lunar) --p
  25. {a="(%.A)([uai]?)l%-([%_%^%.]?[tdrzsnc])", b="ا%2ل%3%3"},
  26. {a="([%(%[%|%<%s%-O])(%.A)([uai]?)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%3ل%4%4"}, --p
  27. {a="%.A", b="ا"},
  28. -- hard coded hamza
  29. {a="|\"'", b="ء"},
  30. {a="A\"'", b="آ"},
  31. {a="[au]\"'", b="أ"},
  32. {a="w\"'", b="ؤ"},
  33. {a="i\"'", b="إ"},
  34. {a="y\"'", b="ئ"},
  35. {a="ؤ([^uaiUAI])", b="ؤْ%1"},
  36. {a="ؤ(%p*)$", b="ؤْ%1"},
  37. {a="ؤ(%p*%s)", b="ؤْ%1"},
  38. {a="أ([^uaiUAI])", b="أْ%1"},
  39. {a="أ(%p*)$", b="أْ%1"},
  40. {a="أ(%p*%s)", b="أْ%1"},
  41. {a="ئ([^uaiUAI])", b="ئْ%1"},
  42. {a="ئ(%p*)$", b="ئْ%1"},
  43. {a="ئ(%p*%s)", b="ئْ%1"},
  44. -- hamza takes tašdīd too
  45. {a="''([Uu])", b="ؤؤ%1"},
  46. {a="''([Aa])", b="أأ%1"},
  47. {a="''([Ii])", b="ئئ%1"},
  48. -- inseparable adverbial particle 'a- + 'a
  49. {a="\'(a)%-\'(a)", b="أ%1اأ%2"},
  50. -- initial long u and i (for a, see below)
  51. {a="%'%_U", b="أU"},
  52. {a="%'%_I", b="إI"},
  53. -- taḫfīfu 'l-hamza
  54. {a="'u'([^uaiUAI])", b="أU%1"},
  55. {a="'i'([^uaiUAI])", b="إI%1"},
  56. {a="([wf]a)%-\'([^uaiUAIl][^%-])", b="%1أْ%2"},
  57. {a="^u'([^uaiUAI])", b="اU%1"},
  58. {a="([^uaiUAIYN][%s%(%[%<])u'([^uaiUAI])", b="%1اU%2"},
  59. {a="^i'([^uaiUAI])", b="اI%1"},
  60. {a="([^uaiUAIYN][%s%(%[%<])i'([^uaiUAI])", b="%1اI%2"},
  61. -- madda (historic writing below)
  62. {a="'a'([^uaiUAI])", b="آ%1"},
  63. {a="([^uiyUI])\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"},
  64. {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"},
  65. {a="\'a?A(O[%_%^%.]?[%`%'btjghxdrzsfqklmnywAY]-O)", b="آ"},
  66. {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"},
  67. {a="(A)(O%'[%S]-O)", b="آ"},
  68. {a="(A)(')(uN?%p*)$", b="aآء%3"},
  69. {a="(A)(')(uN?)(%p*%s)", b="aآء%3%4"},
  70. {a="(A)(')(iN?%p*)$", b="aآء%3"},
  71. {a="(A)(')(iN?)(%p*%s)", b="aآء%3%4"},
  72. {a="(A)(')([iI])", b="aآئ%3"}, -- historic madda
  73. {a="(A)(')(u)", b="aآؤ%3"}, -- historic madda
  74. {a="(A)(')", b="aآء"}, -- historic madda
  75. -- initial (needs both ^ and %W patterns)
  76. -- 'aw: the diphthong is to be resolved into 'awi' (next 8 lines)
  77. {a="^('aw)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1i"},
  78. {a="(%W)('aw)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1%2i"},
  79. {a="^('aw)(O)([%(%[%|%<]?\"?[uai])([%S]-O)", b="%1i"},
  80. {a="(%W)('aw)(O)([%(%[%|%<]?\"?[uai])([%S]-O)", b="%1%2i"},
  81. {a="^('aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"},
  82. {a="(%W)('aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1%2i%3%4"},
  83. {a="^('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"},
  84. {a="(%W)('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"},
  85. -- then the 'initial' rules for the remaining cases
  86. {a="^(')([ua])", b="أ%2"},
  87. {a="^(')(i)", b="إ%2"},
  88. -- consider replacing initial %W with [%s%(%[%<%-]:
  89. -- {a="(%W)(')([ua])", b="%1أ%3"},
  90. -- {a="(%W)(')(i)", b="%1إ%3"},
  91. {a="([%s%(%[%<%-])(')([ua])", b="%1أ%3"},
  92. {a="([%s%(%[%<%-])(')(i)", b="%1إ%3"},
  93. -- final
  94. -- mi'aT is special orthography (unlike ^say'aN and .zim'aN):
  95. -- {a="(%^sa%.?[yY])(\"?%|?)(%')(aN)", b="%1%2ئ%4"}, --new
  96. -- {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, --new
  97. {a="(mi)(%')(a[Tt])", b="%1ائ%3"},
  98. {a="(mi)(%')(aN%_?[AY])", b="%1أ%3"},
  99. -- final hamzah is on the line after a letter of prolongation or a
  100. -- consonant with sukūn
  101. {a="([^Auai])(')(\"?[uai]N?)(%p*)$", b="%1ء%3%4"}, --new
  102. {a="([^Auai])(')(\"?[uai]N?)(%p*%s)", b="%1ء%3%4"},
  103. -- u
  104. {a="(u)(')([uai]N?%p*)$", b="%1ؤ%3"},
  105. {a="(u)(')([uai]N?)(%p*%s)", b="%1ؤ%3%4"},
  106. {a="(u)(')(%p*)$", b="%1ؤْ%3"},
  107. {a="(u)(')(%p*%s)", b="%1ؤْ%3"},
  108. -- a
  109. {a="(a)(')(A%p*)$", b="%1آ"},
  110. {a="(a)(')(A)(%p*%s)", b="%1آ%4"},
  111. {a="(a)(')([u]N?%p*)$", b="%1أ%3"},
  112. {a="(a)(')([u]N?)(%p*%s)", b="%1أ%3%4"},
  113. {a="(a)(')(a%p*)$", b="%1أ%3"},
  114. {a="(a)(')(a)(%p*%s)", b="%1أ%3%4"},
  115. {a="(a)(')(aN%p*)$", b="%1أً"},
  116. {a="(a)(')(aN)(%p*%s)", b="%1أً%4"},
  117. {a="(a)(')([i]N?%p*)$", b="%1إ%3"},
  118. {a="(a)(')([i]N?)(%p*%s)", b="%1إ%3%4"},
  119. {a="(a)(')(%p*)$", b="%1أْ%3"},
  120. {a="(a)(')(%p*%s)", b="%1أْ%3"},
  121. -- i
  122. {a="(i)(')([uai]N?%p*)$", b="%1ئ%3"},
  123. {a="(i)(')([uai]N?)(%p*%s)", b="%1ئ%3%4"},
  124. {a="(i)(')(%p*)$", b="%1ئْ%3"},
  125. {a="(i)(')(%p*%s)", b="%1ئْ%3"},
  126. --
  127. -- middle
  128. {a="([UIwy])(')", b="%1ء"}, --new
  129. -- {a="([Iy])(')", b="%1ئ"}, --included in the above line
  130. {a="([^uai])(')([uU])", b="%1ؤ%3"},
  131. {a="([^uai])(')(%_?[aAY])", b="%1أ%3"},
  132. {a="([^uai])(')([iI])", b="%1ئ%3"},
  133. {a="(u)(')([uU])", b="%1ؤ%3"},
  134. {a="(u)(')(%_?[aAY])", b="%1ؤ%3"},
  135. {a="(u)(')([iI])", b="%1ئ%3"},
  136. {a="(a)(')(%_?[aAY])", b="%1أ%3"},
  137. {a="(a)(')([uU])", b="%1ؤ%3"},
  138. {a="(a)(')([iI])", b="%1ئ%3"},
  139. {a="(i)(')(%_?[aAY])", b="%1ئ%3"},
  140. {a="(i)(')([uU])", b="%1ئ%3"},
  141. {a="(i)(')([iI])", b="%1ئ%3"},
  142. {a="(a)(')([^uaiUAI])", b="%1أْ%3"},
  143. {a="(u)(')([^uaiUAI])", b="%1ؤْ%3"},
  144. {a="(i)(')([^uaiUAI])", b="%1ئْ%3"}
  145. }
  146. hamzafveasy = { -- differences marked below with 'easy'
  147. -- next line for ʾiʿrāb hyphen
  148. {a="(')(%-)([uaiUAI])", b="%1%3"},
  149. -- next lines for ʾalif alone
  150. {a="(%.A)([uai]?)l%-(%^n)", b="ا%2ل%3"}, --additional (^n is lunar)
  151. {a="([%(%[%|%<%s%-O])(%.A)([uai]?)l%-(%^n)", b="%1ا%3%4"}, --additional (^n is lunar) --p
  152. {a="(%.A)([uai]?)l%-([%_%^%.]?[tdrzsnc])", b="ا%2ل%3%3"},
  153. {a="([%(%[%|%<%s%-O])(%.A)([uai]?)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%3ل%4%4"}, --p
  154. {a="%.A", b="ا"},
  155. -- hard coded hamza
  156. {a="|\"'", b="ء"},
  157. {a="A\"'", b="آ"},
  158. {a="[au]\"'", b="أ"},
  159. {a="w\"'", b="ؤ"},
  160. {a="i\"'", b="إ"},
  161. {a="y\"'", b="ئ"},
  162. {a="ؤ([^uaiUAI])", b="ؤْ%1"},
  163. {a="ؤ(%p*)$", b="ؤْ%1"},
  164. {a="ؤ(%p*%s)", b="ؤْ%1"},
  165. {a="أ([^uaiUAI])", b="أْ%1"},
  166. {a="أ(%p*)$", b="أْ%1"},
  167. {a="أ(%p*%s)", b="أْ%1"},
  168. {a="ئ([^uaiUAI])", b="ئْ%1"},
  169. {a="ئ(%p*)$", b="ئْ%1"},
  170. {a="ئ(%p*%s)", b="ئْ%1"},
  171. -- hamza takes tašdīd too
  172. {a="''([Uu])", b="ؤؤ%1"},
  173. {a="''([Aa])", b="أأ%1"},
  174. {a="''([Ii])", b="ئئ%1"},
  175. -- inseparable adverbial particle 'a- + 'a
  176. {a="\'(a)%-\'(a)", b="أ%1اأ%2"},
  177. -- initial long u and i (for a, see below)
  178. {a="%'%_U", b="أU"},
  179. {a="%'%_I", b="إI"},
  180. -- taḫfīfu 'l-hamza
  181. {a="'u'([^uaiUAI])", b="أU%1"},
  182. {a="'i'([^uaiUAI])", b="إI%1"},
  183. {a="([wf]a)%-\'([^uaiUAIl][^%-])", b="%1أْ%2"},
  184. {a="^u'([^uaiUAI])", b="اU%1"},
  185. {a="([^uaiUAIYN][%s%(%[%<])u'([^uaiUAI])", b="%1اU%2"},
  186. {a="^i'([^uaiUAI])", b="اI%1"},
  187. {a="([^uaiUAIYN][%s%(%[%<])i'([^uaiUAI])", b="%1اI%2"},
  188. -- madda (historic writing below)
  189. {a="'a'([^uaiUAI])", b="آ%1"},
  190. {a="([^uiyUI])\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"},
  191. {a="^\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="آ%1"},
  192. {a="\'a?A(O[%_%^%.]?[%`%'btjghxdrzsfqklmnywAY]-O)", b="آ"},
  193. {a="(%W)\'a?A([%_%^%.]?[%`%'btjghxdrzsfqklmnywAY])", b="%1آ%2"},
  194. --easy (begin)
  195. {a="(A)(O%'[%S]-O)", b="ا"},
  196. {a="(A)(')(uN?%p*)$", b="aاء%3"},
  197. {a="(A)(')(uN?)(%p*%s)", b="aاء%3%4"},
  198. {a="(A)(')(iN?%p*)$", b="aاء%3"},
  199. {a="(A)(')(iN?)(%p*%s)", b="aاء%3%4"},
  200. {a="(A)(')([iI])", b="aائ%3"}, -- historic madda
  201. {a="(A)(')(u)", b="aاؤ%3"}, -- historic madda
  202. {a="(A)(')", b="aاء"}, -- historic madda
  203. --easy (end)
  204. -- initial (needs both ^ and %W patterns)
  205. -- 'aw: the diphthong is to be resolved into 'awi' (next 8 lines)
  206. {a="^('aw)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1i"},
  207. {a="(%W)('aw)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1%2i"},
  208. {a="^('aw)(O)([%(%[%|%<]?\"?[uai])([%S]-O)", b="%1i"},
  209. {a="(%W)('aw)(O)([%(%[%|%<]?\"?[uai])([%S]-O)", b="%1%2i"},
  210. {a="^('aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"},
  211. {a="(%W)('aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1%2i%3%4"},
  212. {a="^('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"},
  213. {a="(%W)('aw)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"},
  214. -- then the 'initial' rules for the remaining cases
  215. {a="^(')([ua])", b="أ%2"},
  216. {a="^(')(i)", b="إ%2"},
  217. -- consider replacing initial %W with [%s%(%[%<%-]:
  218. -- {a="(%W)(')([ua])", b="%1أ%3"},
  219. -- {a="(%W)(')(i)", b="%1إ%3"},
  220. {a="([%s%(%[%<%-])(')([ua])", b="%1أ%3"},
  221. {a="([%s%(%[%<%-])(')(i)", b="%1إ%3"},
  222. -- final
  223. -- mi'aT is special orthography (unlike ^say'aN and .zim'aN)
  224. -- {a="(%^sa%.?[yY])(\"?%|?)(%')(aN)", b="%1%2ئ%4"}, --new
  225. -- {a="(.zi?m)(%')(aN)", b="%1ئ%3"}, --new
  226. {a="(mi)(%')(a[Tt])", b="%1ائ%3"},
  227. {a="(mi)(%')(aN%_?[AY])", b="%1أ%3"},
  228. -- easy (begin)
  229. -- The Munjid says that such words as radI'aN do not have the
  230. -- hamzah alone on the line, so take out the following two lines
  231. -- (final hamzah is on the line after a letter of prolongation or a
  232. -- consonant with sukūn)
  233. -- {a="([^Auai])(')(\"?[uai]N?)(%p*)$", b="%1ء%3%4"}, --new
  234. -- {a="([^Auai])(')(\"?[uai]N?)(%p*%s)", b="%1ء%3%4"},
  235. {a="([^Auai])(')(\"?aN)(%p*)$", b="%1ئ%3%4"}, --new
  236. {a="([^Auai])(')(\"?aN)(%p*%s)", b="%1ئ%3%4"}, --new
  237. {a="([^uai])(')(\"?a)(%p*)$", b="%1ء%3%4"}, --new
  238. {a="([^uai])(')(\"?a)(%p*%s)", b="%1ء%3%4"}, --new
  239. {a="([^uai])(')(\"?[ui]N?)(%p*)$", b="%1ء%3%4"}, --new
  240. {a="([^uai])(')(\"?[ui]N?)(%p*%s)", b="%1ء%3%4"}, --new
  241. --easy (end)
  242. -- u
  243. {a="(u)(')([uai]N?%p*)$", b="%1ؤ%3"},
  244. {a="(u)(')([uai]N?)(%p*%s)", b="%1ؤ%3%4"},
  245. {a="(u)(')(%p*)$", b="%1ؤْ%3"},
  246. {a="(u)(')(%p*%s)", b="%1ؤْ%3"},
  247. -- a
  248. {a="(a)(')(A%p*)$", b="%1آ"},
  249. {a="(a)(')(A)(%p*%s)", b="%1آ%4"},
  250. {a="(a)(')([u]N?%p*)$", b="%1أ%3"},
  251. {a="(a)(')([u]N?)(%p*%s)", b="%1أ%3%4"},
  252. {a="(a)(')(a%p*)$", b="%1أ%3"},
  253. {a="(a)(')(a)(%p*%s)", b="%1أ%3%4"},
  254. {a="(a)(')(aN%p*)$", b="%1أً"},
  255. {a="(a)(')(aN)(%p*%s)", b="%1أً%4"},
  256. {a="(a)(')([i]N?%p*)$", b="%1إ%3"},
  257. {a="(a)(')([i]N?)(%p*%s)", b="%1إ%3%4"},
  258. {a="(a)(')(%p*)$", b="%1أْ%3"},
  259. {a="(a)(')(%p*%s)", b="%1أْ%3"},
  260. -- i
  261. {a="(i)(')([uai]N?%p*)$", b="%1ئ%3"},
  262. {a="(i)(')([uai]N?)(%p*%s)", b="%1ئ%3%4"},
  263. {a="(i)(')(%p*)$", b="%1ئْ%3"},
  264. {a="(i)(')(%p*%s)", b="%1ئْ%3"},
  265. --
  266. -- middle
  267. {a="([Uw])(')", b="%1ء"}, --new
  268. {a="([Iy])(')", b="%1ئ"}, --easy
  269. {a="([^uai])(')([uU])", b="%1ؤ%3"},
  270. {a="([^uai])(')(%_?[aAY])", b="%1أ%3"},
  271. {a="([^uai])(')([iI])", b="%1ئ%3"},
  272. {a="(u)(')([uU])", b="%1ؤ%3"},
  273. {a="(u)(')(%_?[aAY])", b="%1ؤ%3"},
  274. {a="(u)(')([iI])", b="%1ئ%3"},
  275. {a="(a)(')(%_?[aAY])", b="%1أ%3"},
  276. {a="(a)(')([uU])", b="%1ؤ%3"},
  277. {a="(a)(')([iI])", b="%1ئ%3"},
  278. {a="(i)(')(%_?[aAY])", b="%1ئ%3"},
  279. {a="(i)(')([uU])", b="%1ئ%3"},
  280. {a="(i)(')([iI])", b="%1ئ%3"},
  281. {a="(a)(')([^uaiUAI])", b="%1أْ%3"},
  282. {a="(u)(')([^uaiUAI])", b="%1ؤْ%3"},
  283. {a="(i)(')([^uaiUAI])", b="%1ئْ%3"}
  284. }
  285. tanwinfv = { -- with assimilations (\SetArbDflt*)
  286. -- assimilations (begin)
  287. {a="(O[%S]-)(%-?[uai]N[UI]?)(O)([rlmnwy])", b="%4%4"},
  288. {a="(%-?[uai]NU)(%s)([rlmnwy])", b="%1%2%3%3"},
  289. -- assimilations (end)
  290. {a="(O[%S]-)(%-?[uai]N[UI]?)(O)([uai])", b="ٱ"},
  291. {a="%-?(uNU)(%s)([uai])", b="%1%2ٱ"},
  292. {a="%-?(aNU)(%s)([uai])", b="%1%2ٱ"},
  293. {a="%-?(iNU)(%s)([uai])", b="%1%2ٱ"},
  294. {a="%-?uNU", b="ٌو"},
  295. {a="%-?aNU", b="ًوا"},
  296. {a="%-?iNU", b="ٍو"},
  297. {a="%-?([uai]N)(%s)([uai])", b="%1%2ٱ"},
  298. {a="%-?(aN[%_]?[AY])(%s)([uai])", b="%1%2ٱ"},
  299. -- assimilations (begin)
  300. {a="%-?(uN)(%s)([rlmnwy])", b="ٌ%2%3%3"},
  301. {a="(O[%S]-)(%-?aN)(_A)(O)([rlmnwy])", b="%5%5"},
  302. {a="(O[%S]-)(%-?aN)(Y)(O)([rlmnwy])", b="%5%5"},
  303. {a="%-?(aN)(_A)(%s)([rlmnwy])", b="ًى%3%4%4"},
  304. {a="%-?(aN)(Y)(%s)([rlmnwy])", b="ًى%3%4%4"},
  305. {a="(T)%-?(aN)(%s)([rlmnwy])", b="%1ً%3%4%4"},
  306. -- {a="(ء)%-?(aN)(%s)([rlmnwy])", b="%1%2%3%4%4"}, --new
  307. {a="([^TA])%-?(aN)(%s)([rlmnwy])", b="%1ًا%3%4%4"},
  308. {a="%-?(iNI?)(%s)([rlmnwy])", b="ٍ%2%3%3"},
  309. -- assimilations (end)
  310. {a="(O[%S]-)(%-?aN)(_A)(O)([uai])", b="ٱ"},
  311. {a="(O[%S]-)(%-?aN)(Y)(O)([uai])", b="ٱ"},
  312. -- quoted tanwīn (begin)
  313. {a="%-?(\"uN)", b=""},
  314. {a="(B)%-?(\"aN)", b="%1"},
  315. {a="%-?(\"aN)(_A)", b="ى"},
  316. {a="%-?(\"aN)(Y)", b="ى"},
  317. {a="(T)%-?(\"aN)", b="%1"},
  318. {a="([اآ])(ء)%-?(\"aN)", b="%1%2"}, --new
  319. {a="([^TA])%-?(\"aN)", b="%1ا"},
  320. {a="%-?(\"iNI?)", b=""},
  321. -- quoted tanwīn (end)
  322. {a="%-?(uN)", b="ٌ"},
  323. {a="(B)%-?(aN)", b="%1ً"},
  324. -- needed by \arbcolor:
  325. {a="%-?(aN)(O[%S]-%_AO)", b="ً"},
  326. {a="%-?(aN)(O[%S]-YO)", b="ً"},
  327. {a="(O[%S]-TO)%-?(aN)", b="ً"},
  328. {a="(O[%S]-)([اآ])(ء)(O)%-?(aN)", b="ً"}, --new
  329. {a="(O[%S]-[^TA]O)%-?(aN)", b="ًا"},
  330. --
  331. {a="%-?(aN)(_A)", b="ًى"},
  332. {a="%-?(aN)(Y)", b="ًى"},
  333. {a="(T)%-?(aN)", b="%1ً"},
  334. {a="([اآ])(ء)%-?(aN)", b="%1%2ً"}, --new
  335. {a="([^TA])%-?(aN)", b="%1ًا"},
  336. {a="%-?(iNI?)", b="ٍ"}
  337. }
  338. tanwinfveasy = { -- no assimilations (see below)
  339. -- assimilations (begin)
  340. --easy {a="(O[%S]-)(%-?[uai]N[UI]?)(O)([rlmnwy])", b="%4%4"},
  341. --easy {a="(%-?[uai]NU)(%s)([rlmnwy])", b="%1%2%3%3"},
  342. -- assimilations (end)
  343. {a="(O[%S]-)(%-?[uai]N[UI]?)(O)([uai])", b="ٱ"},
  344. {a="%-?(uNU)(%s)([uai])", b="%1%2ٱ"},
  345. {a="%-?(aNU)(%s)([uai])", b="%1%2ٱ"},
  346. {a="%-?(iNU)(%s)([uai])", b="%1%2ٱ"},
  347. {a="%-?uNU", b="ٌو"},
  348. {a="%-?aNU", b="ًوا"},
  349. {a="%-?iNU", b="ٍو"},
  350. {a="%-?([uai]N)(%s)([uai])", b="%1%2ٱ"},
  351. {a="%-?(aN[%_]?[AY])(%s)([uai])", b="%1%2ٱ"},
  352. -- assimilations (begin)
  353. --easy {a="%-?(uN)(%s)([rlmnwy])", b="ٌ%2%3%3"},
  354. --easy {a="(O[%S]-)(%-?aN)(_A)(O)([rlmnwy])", b="%5%5"},
  355. --easy {a="(O[%S]-)(%-?aN)(Y)(O)([rlmnwy])", b="%5%5"},
  356. --easy {a="%-?(aN)(_A)(%s)([rlmnwy])", b="ًى%3%4%4"},
  357. --easy {a="%-?(aN)(Y)(%s)([rlmnwy])", b="ًى%3%4%4"},
  358. --easy {a="(T)%-?(aN)(%s)([rlmnwy])", b="%1ً%3%4%4"},
  359. --easy {a="(ء)%-?(aN)(%s)([rlmnwy])", b="%1%2%3%4%4"}, --new
  360. --easy {a="([^TA])%-?(aN)(%s)([rlmnwy])", b="%1ًا%3%4%4"},
  361. --easy {a="%-?(iNI?)(%s)([rlmnwy])", b="ٍ%2%3%3"},
  362. -- assimilations (end)
  363. {a="(O[%S]-)(%-?aN)(_A)(O)([uai])", b="ٱ"},
  364. {a="(O[%S]-)(%-?aN)(Y)(O)([uai])", b="ٱ"},
  365. -- quoted tanwīn (begin)
  366. {a="%-?(\"uN)", b=""},
  367. {a="(B)%-?(\"aN)", b="%1"},
  368. {a="%-?(\"aN)(_A)", b="ى"},
  369. {a="%-?(\"aN)(Y)", b="ى"},
  370. {a="(T)%-?(\"aN)", b="%1"},
  371. {a="([اآ])(ء)%-?(\"aN)", b="%1%2"}, --new
  372. {a="([^TA])%-?(\"aN)", b="%1ا"},
  373. {a="%-?(\"iNI?)", b=""},
  374. -- quoted tanwīn (end)
  375. {a="%-?(uN)", b="ٌ"},
  376. {a="(B)%-?(aN)", b="%1ً"},
  377. -- needed by \arbcolor:
  378. {a="%-?(aN)(O[%S]-%_AO)", b="ً"},
  379. {a="%-?(aN)(O[%S]-YO)", b="ً"},
  380. {a="(O[%S]-TO)%-?(aN)", b="ً"},
  381. {a="(O[%S]-)([اآ])(ء)(O)%-?(aN)", b="ً"}, --new
  382. {a="(O[%S]-[^TA]O)%-?(aN)", b="ًا"},
  383. --
  384. {a="%-?(aN)(_A)", b="ًى"},
  385. {a="%-?(aN)(Y)", b="ًى"},
  386. {a="(T)%-?(aN)", b="%1ً"},
  387. {a="([اآ])(ء)%-?(aN)", b="%1%2ً"}, --new
  388. {a="([^TA])%-?(aN)", b="%1ًا"},
  389. {a="%-?(iNI?)", b="ٍ"}
  390. }
  391. trigraphsfv = { -- trigraphs or more
  392. -- ʾalif al-waṣl: put it back on with \arbnull
  393. {a="(O[%S]-)([%'a]l%-)(O)(\"?[uai])", b="ٱ"},
  394. -- 'llatI / 'llad_I
  395. {a="^'ll(a)([%_]?[dt])", b="ٱلّ%1%2"},
  396. {a="([%(%[%|%<%s%-])'ll(a)([%_]?[dt])", b="%1ٱلّ%2%3"}, --p
  397. -- law: the diphthong is to be resolved into 'awi' (next 8 lines)
  398. {a="^(law)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1i"},
  399. {a="(%W)(law)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1%2i"},
  400. {a="^(law)(O)(\"?[uai])([%S]-O)", b="%1i"},
  401. {a="(%W)(law)(O)(\"?[uai])([%S]-O)", b="%1%2i"},
  402. {a="^(law)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"},
  403. {a="(%W)(law)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1%2i%3%4"},
  404. {a="^(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"},
  405. {a="(%W)(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"},
  406. -- al- + lām
  407. {a="^(a)l%-(l)", b="ا%1ل%2%2"},
  408. {a="([%(%[%|%<%s%-O])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p
  409. -- al- + solar consonant ('c' and '^n' are additional characters)
  410. {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar
  411. {a="([%(%[%|%<%s%-O])(a)l%-(%^n)", b="%1ا%2ل%3"}, -- ^n is lunar --p
  412. {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2%2"},
  413. {a="([%(%[%|%<%s%-O])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3%3"}, --p
  414. -- assim. art. + solar consonant ('c' and '^n' are additional characters)
  415. {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar
  416. {a="([%(%[%|%<%s%-O])(a)(%^n)%-", b="%1ا%2ل"}, -- ^n is lunar --p
  417. {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل%2"},
  418. {a="([%(%[%|%<%s%-O])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل%3"}, --p
  419. -- al- + initial unstable hamza
  420. {a="^(a)l%-(\"?[uai])", b="ا%1ل%2ٱ"},
  421. {a="([%(%[%|%<%s%-O])(a)l%-(\"?[uai])", b="%1ا%2ل%3ٱ"}, --p
  422. -- li-/la + art. + initial unstable hamza is a special orthography
  423. {a="l([ai])%-l%-(\"?[uai])", b="ل%1ل%2ٱ"},
  424. -- al- + lunar consonant (i.e. what remains)
  425. {a="^(a)l%-", b="ا%1لْ"},
  426. {a="([%(%[%|%<%s%-O])(a)l%-", b="%1ا%2لْ"}, --p
  427. -- diphthongs to be resolved before ʾalif conjunctionis
  428. {a="(aW)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="awuا"},
  429. {a="(aw)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1u"},
  430. {a="(ay)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1i"},
  431. {a="(aW)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="awuا%2%3"},
  432. {a="(aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1u%2%3"},
  433. {a="(ay)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"},
  434. -- art. with waṣla + lām
  435. {a="'l%-(l)", b="ٱل%1%1"},
  436. -- art. with waṣla + solar consonant
  437. -- ('c' and '^n' are additional characters)
  438. {a="'l%-(%^n)", b="ٱل%1"}, -- ^n is lunar
  439. {a="'l%-([%_%^%.]?[tdrzsnc])", b="ٱل%1%1"},
  440. -- li-/la- + art. + lām
  441. {a="l([ai])%-l%-(l)", b="ل%1%2%2"},
  442. -- assim. art. with waṣla + solar consonant
  443. -- ('c' and '^n' are additional characters)
  444. {a="'(%^n)%-", b="ٱل"}, -- ^n is lunar
  445. {a="'([%_%^%.]?[tdrzsnc])%-", b="ٱل%1"},
  446. -- li-/la- + art. + solar consonant is a special orthography
  447. -- ('c' and '^n' are additional characters)
  448. {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- ^n is lunar
  449. {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2%2"},
  450. -- li-/la- + assim. art. + solar consonant is a special orthography
  451. -- ('c' and '^n' are additional characters)
  452. {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar
  453. {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3%3"},
  454. -- art. with waṣla + initial unstable hamza
  455. {a="'l%-(\"?[uai])", b="ٱل%1ٱ"},
  456. -- art. with waṣla + lunar consonant (i.e. what remains)
  457. {a="'l%-", b="ٱلْ"},
  458. -- the silent wāw
  459. {a="uU(%p*)$", b="uو%1"},
  460. {a="uU(%p*%s)", b="uو%1"},
  461. {a="aU(%p*)$", b="aو%1"},
  462. {a="aU(%p*%s)", b="aو%1"},
  463. {a="iU(%p*)$", b="iو%1"},
  464. {a="iU(%p*%s)", b="iو%1"},
  465. -- words ending in -āT with silent wāw/yāʾ
  466. {a="(_a)UA", b="%1وا"},
  467. {a="(_a)U", b="%1و"},
  468. {a="(_a)I", b="%1ي"}
  469. }
  470. -- idgham/assimilation rules for trigraphs apply here : see voc lua
  471. -- file.
  472. trigraphsfveasy = { -- trigraphs or more (see 'easy' tag below for the diffs)
  473. -- ʾalif al-waṣl: put it back on with \arbnull
  474. {a="(O[%S]-)([%'a]l%-)(O)(\"?[uai])", b="ٱ"},
  475. -- 'llatI / 'llad_I
  476. {a="^'ll(a)([%_]?[dt])", b="ٱلّ%1%2"},
  477. {a="([%(%[%|%<%s%-])'ll(a)([%_]?[dt])", b="%1ٱلّ%2%3"}, --p
  478. -- law: the diphthong is to be resolved into 'awi' (next 8 lines)
  479. {a="^(law)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1i"},
  480. {a="(%W)(law)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1%2i"},
  481. {a="^(law)(O)(\"?[uai])([%S]-O)", b="%1i"},
  482. {a="(%W)(law)(O)(\"?[uai])([%S]-O)", b="%1%2i"},
  483. {a="^(law)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"},
  484. {a="(%W)(law)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1%2i%3%4"},
  485. {a="^(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1i%2%3"},
  486. {a="(%W)(law)(%s)([%(%[%|%<]?\"?[uai])", b="%1%2i%3%4"},
  487. -- al- + lām
  488. {a="^(a)l%-(l)", b="ا%1ل%2%2"},
  489. {a="([%(%[%|%<%s%-O])(a)l%-(l)", b="%1ا%2ل%3%3"}, --p
  490. -- al- + solar consonant ('c' and '^n' are additional characters)
  491. {a="^(a)l%-(%^n)", b="ا%1ل%2"}, -- ^n is lunar
  492. {a="([%(%[%|%<%s%-O])(a)l%-(%^n)", b="%1ا%2ل%3"}, -- ^n is lunar --p
  493. {a="^(a)l%-([%_%^%.]?[tdrzsnc])", b="ا%1ل%2%2"},
  494. {a="([%(%[%|%<%s%-O])(a)l%-([%_%^%.]?[tdrzsnc])", b="%1ا%2ل%3%3"}, --p
  495. -- assim. art. + solar consonant ('c' and '^n' are additional characters)
  496. {a="^(a)(%^n)%-", b="ا%1ل"}, -- ^n is lunar
  497. {a="([%(%[%|%<%s%-O])(a)(%^n)%-", b="%1ا%2ل"}, -- ^n is lunar --p
  498. {a="^(a)([%_%^%.]?[tdrzsnc])%-", b="ا%1ل%2"},
  499. {a="([%(%[%|%<%s%-O])(a)([%_%^%.]?[tdrzsnc])%-", b="%1ا%2ل%3"}, --p
  500. -- al- + initial unstable hamza
  501. {a="^(a)l%-(\"?[uai])", b="ا%1ل%2ٱ"},
  502. {a="([%(%[%|%<%s%-O])(a)l%-(\"?[uai])", b="%1ا%2ل%3ٱ"}, --p
  503. -- li-/la + art. + initial unstable hamza is a special orthography
  504. {a="l([ai])%-l%-(\"?[uai])", b="ل%1ل%2ٱ"},
  505. -- al- + lunar consonant (i.e. what remains)
  506. {a="^(a)l%-", b="ا%1لْ"},
  507. {a="([%(%[%|%<%s%-O])(a)l%-", b="%1ا%2لْ"}, --p
  508. -- diphthongs to be resolved before ʾalif conjunctionis
  509. {a="(aW)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="awuا"},
  510. {a="(aw)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1u"},
  511. {a="(ay)(O)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)([%S]-O)", b="%1i"},
  512. {a="(aW)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="awuا%2%3"},
  513. {a="(aw)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1u%2%3"},
  514. {a="(ay)(%s)(['][%_%^%.]?[l'btjghxdrzs`fqkmnwy]%-)", b="%1i%2%3"},
  515. -- art. with waṣla + lām
  516. {a="'l%-(l)", b="ٱل%1%1"},
  517. -- art. with waṣla + solar consonant
  518. -- ('c' and '^n' are additional characters)
  519. {a="'l%-(%^n)", b="ٱل%1"}, -- ^n is lunar
  520. {a="'l%-([%_%^%.]?[tdrzsnc])", b="ٱل%1%1"},
  521. -- li-/la- + art. + lām
  522. {a="l([ai])%-l%-(l)", b="ل%1%2%2"},
  523. -- assim. art. with waṣla + solar consonant
  524. -- ('c' and '^n' are is an additional characters)
  525. {a="'(%^n)%-", b="ٱل"}, -- ^n is lunar
  526. {a="'([%_%^%.]?[tdrzsnc])%-", b="ٱل%1"},
  527. -- li-/la- + art. + solar consonant is a special orthography
  528. -- ('c' and '^n' are additional characters)
  529. {a="l([ai])%-l%-(%^n)", b="ل%1ل%2"}, -- ^n is lunar
  530. {a="l([ai])%-l%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%2%2"},
  531. -- li-/la- + assim. art. + solar consonant is a special orthography
  532. -- ('c and '^n' are additional characters)
  533. {a="l([ai])%-(%^n)%-(%^n)", b="ل%1ل%3"}, -- ^n is lunar
  534. {a="l([ai])%-([%_%^%.]?[tdrzsnc])%-([%_%^%.]?[tdrzsnc])", b="ل%1ل%3%3"},
  535. -- art. with waṣla + initial unstable hamza
  536. {a="'l%-(\"?[uai])", b="ٱل%1ٱ"},
  537. -- art. with waṣla + lunar consonant (i.e. what remains)
  538. {a="'l%-", b="ٱلْ"},
  539. -- the silent wāw
  540. {a="uU(%p*)$", b="uو%1"},
  541. {a="uU(%p*%s)", b="uو%1"},
  542. {a="aU(%p*)$", b="aو%1"},
  543. {a="aU(%p*%s)", b="aو%1"},
  544. {a="iU(%p*)$", b="iو%1"},
  545. {a="iU(%p*%s)", b="iو%1"},
  546. -- words ending in -āT with silent wāw/yāʾ
  547. {a="(_a)UA", b="%1وا"},
  548. {a="(_a)U", b="%1و"},
  549. {a="(_a)I", b="%1ي"}
  550. }
  551. digraphsfvidgham = {
  552. -- ʾiʿrāb: straight double quote must be discarded
  553. {a="(%-)(\"?[UI]na)(%p*%s)", b="%2%3"},
  554. {a="(%-)(\"?[UI]na)(%p*)$", b="%2%3"},
  555. {a="(%-)(\"?At[ui])(%p*%s)", b="%2%3"},
  556. {a="(%-)(\"?At[ui])(%p*)$", b="%2%3"},
  557. {a="(%-)(\"?Ani)(%p*%s)", b="%2%3"},
  558. {a="(%-)(\"?Ani)(%p*)$", b="%2%3"},
  559. {a="(%-)(\"?ayni)(%p*%s)", b="%2%3"},
  560. {a="(%-)(\"?ayni)(%p*)$", b="%2%3"},
  561. {a="(%-)(\"?[uai])(%p*%s)", b="%2%3"},
  562. {a="(%-)(\"?[uai])(%p*)$", b="%2%3"},
  563. -- ʾiʿrāb (end)
  564. -- initial straight double quote gives a connective ʾalif
  565. {a="^\"[uai]", b="ٱ"},
  566. {a="([%(%[%|%<%s%-])\"[uai]", b="%1ٱ"}, --p
  567. -- diphthongs to be resolved before ʾalif conjunctionis
  568. {a="(aW)(O)(\"?[uai])([%S]-O)", b="awuا"},
  569. {a="(aW)(%s)([%(%[%|%<]?)(\"?[uai])", b="awuا%2%3ٱ"}, --p
  570. {a="(aw)(O)(\"?[uai])([%S]-O)", b="%1u"},
  571. {a="(aw)(%s)([%(%[%|%<]?)(\"?[uai])", b="%1u%2%3ٱ"}, --p
  572. {a="(ay)(O)(\"?[uai])([%S]-O)", b="%1i"},
  573. {a="(ay)(%s)([%(%[%|%<]?)(\"?[uai])", b="%1i%2%3ٱ"}, --p
  574. -- hyphen + initial alif without hamza
  575. -- {a="([uai]%-)(\"?[uai])", b="%1ٱ"},
  576. {a="([uai]%-)(\"?[uai])([%^%_%.%`]?)([%aأإؤئ])", b="%1ٱ%3%4"},
  577. -- initial alif without hamza (next 4 lines)
  578. {a="(O[%S]-)([uaiUAIY])(O)(\"?[uai])", b="ٱ"},
  579. {a="([%_]?[uaiUAIY])(%s[%(%[%|%<]?)(\"?[uai])", b="%1%2ٱ"}, --p
  580. {a="^([%(%[%|%<]?)(\"?[uai])", b="%1ا%2"}, --p
  581. {a="(%s)([%(%[%|%<]?)(\"?[uai])", b="%1%2ا%3"}, --p
  582. {a="%-%-", b="ـ"},
  583. {a="ؤؤ", b="ؤّ"},
  584. {a="أأ", b="أّ"},
  585. {a="ئئ", b="ئّ"},
  586. {a="bb", b="بّ"},
  587. {a="BB", b="ـّ"},
  588. {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"},
  589. -- same as above for additional characters:
  590. {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"},
  591. {a="tt", b="تّ"},
  592. {a="%_t%_t", b="ثّ"},
  593. {a="jj", b="جّ"},
  594. {a="%^g%^g", b="جّ"},
  595. {a="%.h%.h", b="حّ"},
  596. {a="xx", b="خّ"},
  597. {a="%_h%_h", b="خّ"},
  598. {a="dd", b="دّ"},
  599. {a="%_d%_d", b="ذّ"},
  600. {a="rr", b="رّ"},
  601. {a="zz", b="زّ"},
  602. {a="ss", b="سّ"},
  603. {a="%^s%^s", b="شّ"},
  604. {a="%.s%.s", b="صّ"},
  605. {a="%.d%.d", b="ضّ"},
  606. {a="%.t%.t", b="طّ"},
  607. {a="%.z%.z", b="ظّ"},
  608. {a="%`%`", b="عّ"},
  609. {a="%.g%.g", b="غّ"},
  610. {a="ff", b="فّ"},
  611. {a="qq", b="قّ"},
  612. {a="kk", b="كّ"},
  613. {a="ll", b="لّ"},
  614. {a="mm", b="مّ"},
  615. {a="nn", b="نّ"},
  616. {a="hh", b="هّ"},
  617. {a="ww", b="وّ"},
  618. {a="yy", b="يّ"},
  619. {a="%.y%.y", b="ىّ"},
  620. -- additional characters + šaddah (begin)
  621. {a="pp", b="پّ"},
  622. {a="vv", b="ڤّ"},
  623. {a="gg", b="گّ"},
  624. {a="%^c%^c", b="چّ"},
  625. {a="%^z%^z", b="ژّ"},
  626. {a="%^n%^n", b="ڭّ"},
  627. -- additional characters + šaddah (end)
  628. -- sukūn begin
  629. -- first, take out hyphen if any (next two lines):
  630. {a="([ai]Y)%-([uaiUAI])", b="%1%2"},
  631. {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"},
  632. {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p*)$", b="%1ْ%2"},
  633. {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p*%s)", b="%1ْ%2"},
  634. {a="([ai]Y)([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"},
  635. {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"},
  636. -- take out sukūn in cases of assimilation
  637. {a="(n)(ْ)(%s)(ر)", b="%1%3%4"},
  638. {a="(n)(ْ)(%s)(و)", b="%1%3%4"},
  639. {a="(n)(ْ)(%s)(ي)", b="%1%3%4"},
  640. {a="(n)(ْ)(%s)(ل)", b="%1%3%4"},
  641. {a="(n)(ْ)(%s)(م)", b="%1%3%4"},
  642. {a="(n)(ْ)(%s)(ن)", b="%1%3%4"},
  643. {a="ْ\"", b="\""},
  644. -- sukūn end
  645. {a="_t", b="ث"},
  646. {a="%^g", b="ج"},
  647. {a="%.h", b="ح"},
  648. {a="_h", b="خ"},
  649. {a="_d", b="ذ"},
  650. {a="%^s", b="ش"},
  651. {a="%.s", b="ص"},
  652. {a="%.d", b="ض"},
  653. {a="%.t", b="ط"},
  654. {a="%.z", b="ظ"},
  655. {a="%.g", b="غ"},
  656. {a="%.y", b="ى"},
  657. -- additional characters (begin)
  658. {a="%^c", b="چ"},
  659. {a="%^z", b="ژ"},
  660. {a="%^n", b="ڭ"},
  661. -- additional characters (end)
  662. {a="(U)(A)", b="%1ا"},
  663. {a="WA", b="وْا"},
  664. {a="(a)W\"", b="%1وا"},
  665. {a="(a)W", b="%1وْا"},
  666. {a="_A", b="aى"},
  667. {a="_u", b="ٗ"},
  668. {a="_a", b="ٰ"},
  669. {a="_i", b="ٖ"},
  670. {a="%.b", b="ٮ"},
  671. {a="%.f", b="ڡ"},
  672. {a="%.q", b="ٯ"},
  673. {a="%.k", b="ک"},
  674. {a="%.n", b="ں"},
  675. {a="%^d", b="ڊ"}
  676. }
  677. digraphsfv = {
  678. -- iʿrāb: straight double quote must be discarded
  679. {a="(%-)(\"?[UI]na)(%p*%s)", b="%2%3"},
  680. {a="(%-)(\"?[UI]na)(%p*)$", b="%2%3"},
  681. {a="(%-)(\"?At[ui])(%p*%s)", b="%2%3"},
  682. {a="(%-)(\"?At[ui])(%p*)$", b="%2%3"},
  683. {a="(%-)(\"?Ani)(%p*%s)", b="%2%3"},
  684. {a="(%-)(\"?Ani)(%p*)$", b="%2%3"},
  685. {a="(%-)(\"?ayni)(%p*%s)", b="%2%3"},
  686. {a="(%-)(\"?ayni)(%p*)$", b="%2%3"},
  687. {a="(%-)(\"?[uai])(%p*%s)", b="%2%3"},
  688. {a="(%-)(\"?[uai])(%p*)$", b="%2%3"},
  689. -- ʾiʿrāb (end)
  690. -- initial straight double quote gives a connective ʾalif
  691. {a="^\"[uai]", b="ٱ"},
  692. {a="([%(%[%|%<%s%-])\"[uai]", b="%1ٱ"}, --p
  693. -- diphthongs to be resolved before ʾalif conjunctionis
  694. {a="(aW)(O)(\"?[uai])([%S]-O)", b="awuا"},
  695. {a="(aW)(%s)([%(%[%|%<]?)(\"?[uai])", b="awuا%2%3ٱ"}, --p
  696. {a="(aw)(O)(\"?[uai])([%S]-O)", b="%1u"},
  697. {a="(aw)(%s)([%(%[%|%<]?)(\"?[uai])", b="%1u%2%3ٱ"}, --p
  698. {a="(ay)(O)(\"?[uai])([%S]-O)", b="%1i"},
  699. {a="(ay)(%s)([%(%[%|%<]?)(\"?[uai])", b="%1i%2%3ٱ"}, --p
  700. -- hyphen + initial alif without hamza
  701. -- {a="([uai]%-)(\"?[uai])", b="%1ٱ"},
  702. {a="([uai]%-)(\"?[uai])([%^%_%.%`]?)([%aأإؤئ])", b="%1ٱ%3%4"},
  703. -- initial alif without hamza (next 4 lines)
  704. {a="(O[%S]-)([uaiUAIY])(O)(\"?[uai])", b="ٱ"},
  705. {a="([%_]?[uaiUAIY])(%s[%(%[%|%<]?)(\"?[uai])", b="%1%2ٱ"}, --p
  706. {a="^([%(%[%|%<]?)(\"?[uai])", b="%1ا%2"}, --p
  707. {a="(%s)([%(%[%|%<]?)(\"?[uai])", b="%1%2ا%3"}, --p
  708. {a="%-%-", b="ـ"},
  709. {a="ؤؤ", b="ؤّ"},
  710. {a="أأ", b="أّ"},
  711. {a="ئئ", b="ئّ"},
  712. {a="bb", b="بّ"},
  713. {a="BB", b="ـّ"},
  714. {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"},
  715. -- same as above for additional characters:
  716. {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"},
  717. {a="tt", b="تّ"},
  718. {a="%_t%_t", b="ثّ"},
  719. {a="jj", b="جّ"},
  720. {a="%^g%^g", b="جّ"},
  721. {a="%.h%.h", b="حّ"},
  722. {a="xx", b="خّ"},
  723. {a="%_h%_h", b="خّ"},
  724. {a="dd", b="دّ"},
  725. {a="%_d%_d", b="ذّ"},
  726. {a="rr", b="رّ"},
  727. {a="zz", b="زّ"},
  728. {a="ss", b="سّ"},
  729. {a="%^s%^s", b="شّ"},
  730. {a="%.s%.s", b="صّ"},
  731. {a="%.d%.d", b="ضّ"},
  732. {a="%.t%.t", b="طّ"},
  733. {a="%.z%.z", b="ظّ"},
  734. {a="%`%`", b="عّ"},
  735. {a="%.g%.g", b="غّ"},
  736. {a="ff", b="فّ"},
  737. {a="qq", b="قّ"},
  738. {a="kk", b="كّ"},
  739. {a="ll", b="لّ"},
  740. {a="mm", b="مّ"},
  741. {a="nn", b="نّ"},
  742. {a="hh", b="هّ"},
  743. {a="ww", b="وّ"},
  744. {a="yy", b="يّ"},
  745. {a="%.y%.y", b="ىّ"},
  746. -- additional characters + šaddah (begin)
  747. {a="pp", b="پّ"},
  748. {a="vv", b="ڤّ"},
  749. {a="gg", b="گّ"},
  750. {a="%^c%^c", b="چّ"},
  751. {a="%^z%^z", b="ژّ"},
  752. {a="%^n%^n", b="ڭّ"},
  753. -- additional characters + šaddah (end)
  754. -- sukūn begin
  755. -- first, take out hyphen if any (next two lines):
  756. {a="([ai]Y)%-([uaiUAI])", b="%1%2"},
  757. {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"},
  758. {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p*)$", b="%1ْ%2"},
  759. {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p*%s)", b="%1ْ%2"},
  760. {a="([ai]Y)([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"},
  761. {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"},
  762. -- take out sukūn in cases of assimilation
  763. -- {a="(n)(ْ)(%s)(ر)", b="%1%3%4"},
  764. -- {a="(n)(ْ)(%s)(و)", b="%1%3%4"},
  765. -- {a="(n)(ْ)(%s)(ي)", b="%1%3%4"},
  766. -- {a="(n)(ْ)(%s)(ل)", b="%1%3%4"},
  767. -- {a="(n)(ْ)(%s)(م)", b="%1%3%4"},
  768. -- {a="(n)(ْ)(%s)(ن)", b="%1%3%4"},
  769. {a="ْ\"", b="\""},
  770. -- sukūn end
  771. {a="_t", b="ث"},
  772. {a="%^g", b="ج"},
  773. {a="%.h", b="ح"},
  774. {a="_h", b="خ"},
  775. {a="_d", b="ذ"},
  776. {a="%^s", b="ش"},
  777. {a="%.s", b="ص"},
  778. {a="%.d", b="ض"},
  779. {a="%.t", b="ط"},
  780. {a="%.z", b="ظ"},
  781. {a="%.g", b="غ"},
  782. {a="%.y", b="ى"},
  783. -- additional characters (begin)
  784. {a="%^c", b="چ"},
  785. {a="%^z", b="ژ"},
  786. {a="%^n", b="ڭ"},
  787. -- additional characters (end)
  788. {a="(U)(A)", b="%1ا"},
  789. {a="WA", b="وْا"},
  790. {a="(a)W\"", b="%1وا"},
  791. {a="(a)W", b="%1وْا"},
  792. {a="_A", b="aى"},
  793. {a="_u", b="ٗ"},
  794. {a="_a", b="ٰ"},
  795. {a="_i", b="ٖ"},
  796. {a="%.b", b="ٮ"},
  797. {a="%.f", b="ڡ"},
  798. {a="%.q", b="ٯ"},
  799. {a="%.k", b="ک"},
  800. {a="%.n", b="ں"},
  801. {a="%^d", b="ڊ"}
  802. }
  803. digraphsfveasy = { -- see the differences under 'easy' marker below
  804. -- ʾiʿrāb: straight double quote must be discarded
  805. {a="(%-)(\"?[UI]na)(%p*%s)", b="%2%3"},
  806. {a="(%-)(\"?[UI]na)(%p*)$", b="%2%3"},
  807. {a="(%-)(\"?At[ui])(%p*%s)", b="%2%3"},
  808. {a="(%-)(\"?At[ui])(%p*)$", b="%2%3"},
  809. {a="(%-)(\"?Ani)(%p*%s)", b="%2%3"},
  810. {a="(%-)(\"?Ani)(%p*)$", b="%2%3"},
  811. {a="(%-)(\"?ayni)(%p*%s)", b="%2%3"},
  812. {a="(%-)(\"?ayni)(%p*)$", b="%2%3"},
  813. {a="(%-)(\"?[uai])(%p*%s)", b="%2%3"},
  814. {a="(%-)(\"?[uai])(%p*)$", b="%2%3"},
  815. -- ʾiʿrāb (end)
  816. -- initial straight double quote gives a connective ʾalif
  817. {a="^\"[uai]", b="ٱ"},
  818. {a="([%(%[%|%<%s%-])\"[uai]", b="%1ٱ"}, --p
  819. -- diphthongs to be resolved before ʾalif conjunctionis
  820. {a="(aW)(O)(\"?[uai])([%S]-O)", b="awuا"},
  821. {a="(aW)(%s)([%(%[%|%<]?)(\"?[uai])", b="awuا%2%3ٱ"}, --p
  822. {a="(aw)(O)(\"?[uai])([%S]-O)", b="%1u"},
  823. {a="(aw)(%s)([%(%[%|%<]?)(\"?[uai])", b="%1u%2%3ٱ"}, --p
  824. {a="(ay)(O)(\"?[uai])([%S]-O)", b="%1i"},
  825. {a="(ay)(%s)([%(%[%|%<]?)(\"?[uai])", b="%1i%2%3ٱ"}, --p
  826. -- hyphen + initial alif without hamza
  827. -- {a="([uai]%-)(\"?[uai])", b="%1ٱ"},
  828. {a="([uai]%-)(\"?[uai])([%^%_%.%`]?)([%aأإؤئ])", b="%1ٱ%3%4"},
  829. -- initial alif without hamza (next 4 lines)
  830. {a="(O[%S]-)([uaiUAIY])(O)(\"?[uai])", b="ٱ"},
  831. {a="([%_]?[uaiUAIY])(%s[%(%[%|%<]?)(\"?[uai])", b="%1%2ٱ"}, --p
  832. {a="^([%(%[%|%<]?)(\"?[uai])", b="%1ا%2"}, --p
  833. {a="(%s)([%(%[%|%<]?)(\"?[uai])", b="%1%2ا%3"}, --p
  834. {a="%-%-", b="ـ"},
  835. {a="ؤؤ", b="ؤّ"},
  836. {a="أأ", b="أّ"},
  837. {a="ئئ", b="ئّ"},
  838. {a="bb", b="بّ"},
  839. {a="BB", b="ـّ"},
  840. {a="([%_%^%.])([tghdsz])([tghdsz])", b="%1%2|%3"},
  841. -- same as above for additional characters:
  842. {a="([%_%^%.])([cn])([cn])", b="%1%2|%3"},
  843. {a="tt", b="تّ"},
  844. {a="%_t%_t", b="ثّ"},
  845. {a="jj", b="جّ"},
  846. {a="%^g%^g", b="جّ"},
  847. {a="%.h%.h", b="حّ"},
  848. {a="xx", b="خّ"},
  849. {a="%_h%_h", b="خّ"},
  850. {a="dd", b="دّ"},
  851. {a="%_d%_d", b="ذّ"},
  852. {a="rr", b="رّ"},
  853. {a="zz", b="زّ"},
  854. {a="ss", b="سّ"},
  855. {a="%^s%^s", b="شّ"},
  856. {a="%.s%.s", b="صّ"},
  857. {a="%.d%.d", b="ضّ"},
  858. {a="%.t%.t", b="طّ"},
  859. {a="%.z%.z", b="ظّ"},
  860. {a="%`%`", b="عّ"},
  861. {a="%.g%.g", b="غّ"},
  862. {a="ff", b="فّ"},
  863. {a="qq", b="قّ"},
  864. {a="kk", b="كّ"},
  865. {a="ll", b="لّ"},
  866. {a="mm", b="مّ"},
  867. {a="nn", b="نّ"},
  868. {a="hh", b="هّ"},
  869. {a="ww", b="وّ"},
  870. {a="yy", b="يّ"},
  871. {a="%.y%.y", b="ىّ"},
  872. -- additional characters + šaddah (begin)
  873. {a="pp", b="پّ"},
  874. {a="vv", b="ڤّ"},
  875. {a="gg", b="گّ"},
  876. {a="%^c%^c", b="چّ"},
  877. {a="%^z%^z", b="ژّ"},
  878. {a="%^n%^n", b="ڭّ"},
  879. -- additional characters + šaddah (end)
  880. -- sukūn begin ('easy' needs these rules to be taken out); but
  881. -- first take out every previously generated sukūn by hamza rules,
  882. -- so there be no need to edit them:
  883. {a="ْ", b=""},
  884. -- first, take out hyphen if any (next two lines):
  885. -- {a="([ai]Y)%-([uaiUAI])", b="%1%2"},
  886. -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])%-([uaiUAI])", b="%1%2"},
  887. -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p*)$", b="%1ْ%2"},
  888. -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])(%p*%s)", b="%1ْ%2"},
  889. -- {a="([ai]Y)([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"},
  890. -- {a="([%_%^%.]?[Bbtjghxdrzs%`fqklmnwy])([%_]?[^%_uaiUAIYًٌٍ])", b="%1ْ%2"},
  891. -- take out sukūn in cases of assimilation
  892. -- {a="(n)(ْ)(%s)(ر)", b="%1%3%4"},
  893. -- {a="(n)(ْ)(%s)(و)", b="%1%3%4"},
  894. -- {a="(n)(ْ)(%s)(ي)", b="%1%3%4"},
  895. -- {a="(n)(ْ)(%s)([ل])", b="%1%3%4"},
  896. -- {a="(n)(ْ)(%s)([م])", b="%1%3%4"},
  897. -- {a="(n)(ْ)(%s)([ن])", b="%1%3%4"},
  898. -- {a="ْ\"", b="\""},
  899. -- sukūn end
  900. {a="_t", b="ث"},
  901. {a="%^g", b="ج"},
  902. {a="%.h", b="ح"},
  903. {a="_h", b="خ"},
  904. {a="_d", b="ذ"},
  905. {a="%^s", b="ش"},
  906. {a="%.s", b="ص"},
  907. {a="%.d", b="ض"},
  908. {a="%.t", b="ط"},
  909. {a="%.z", b="ظ"},
  910. {a="%.g", b="غ"},
  911. {a="%.y", b="ى"},
  912. -- additional characters (begin)
  913. {a="%^c", b="چ"},
  914. {a="%^z", b="ژ"},
  915. {a="%^n", b="ڭ"},
  916. -- additional characters (end)
  917. {a="(U)(A)", b="%1ا"},
  918. {a="WA", b="وْا"},
  919. {a="(a)W\"", b="%1وا"},
  920. {a="(a)W", b="%1وْا"},
  921. {a="_A", b="aى"},
  922. {a="_u", b="ٗ"},
  923. {a="_a", b="ٰ"},
  924. {a="_i", b="ٖ"},
  925. {a="%.b", b="ٮ"},
  926. {a="%.f", b="ڡ"},
  927. {a="%.q", b="ٯ"},
  928. {a="%.k", b="ک"},
  929. {a="%.n", b="ں"},
  930. {a="%^d", b="ڊ"}
  931. }
  932. singlefv = {
  933. {a="b", b="ب"},
  934. {a="t", b="ت"},
  935. {a="j", b="ج"},
  936. {a="x", b="خ"},
  937. {a="d", b="د"},
  938. {a="r", b="ر"},
  939. {a="z", b="ز"},
  940. {a="s", b="س"},
  941. {a="f", b="ف"},
  942. {a="`", b="ع"},
  943. {a="f", b="ف"},
  944. {a="q", b="ق"},
  945. {a="k", b="ك"},
  946. {a="l", b="ل"},
  947. {a="m", b="م"},
  948. {a="n", b="ن"},
  949. {a="h", b="ه"},
  950. {a="w", b="و"},
  951. {a="y", b="ي"},
  952. {a="T", b="ة"},
  953. -- additional characters (begin)
  954. {a="p", b="پ"},
  955. {a="v", b="ڤ"},
  956. {a="g", b="گ"},
  957. -- additional characters (end)
  958. {a="\"$", b=""},
  959. {a="\"(%W)", b="%1"},
  960. {a="\"([^uaiUAI])", b="%1"},
  961. {a="o", b="ْ"}, -- hard-coded sukūn
  962. {a="([^0-9])%-([^0-9])", b="%1%2"},
  963. {a="B", b="ـ"},
  964. }
  965. singlefveasy = { -- see the differences under 'easy' tag below
  966. {a="b", b="ب"},
  967. {a="t", b="ت"},
  968. {a="j", b="ج"},
  969. {a="x", b="خ"},
  970. {a="d", b="د"},
  971. {a="r", b="ر"},
  972. {a="z", b="ز"},
  973. {a="s", b="س"},
  974. {a="f", b="ف"},
  975. {a="`", b="ع"},
  976. {a="f", b="ف"},
  977. {a="q", b="ق"},
  978. {a="k", b="ك"},
  979. {a="l", b="ل"},
  980. {a="m", b="م"},
  981. {a="n", b="ن"},
  982. {a="h", b="ه"},
  983. {a="w", b="و"},
  984. {a="y", b="ي"},
  985. {a="T", b="ة"},
  986. -- additional characters (begin)
  987. {a="p", b="پ"},
  988. {a="v", b="ڤ"},
  989. {a="g", b="گ"},
  990. -- additional characters (end)
  991. -- easy (begin): \" needs to put back the sukūn
  992. {a="\"$", b="ْ"},
  993. {a="\"(%W)", b="ْ%1"},
  994. {a="\"([^uaiUAI])", b="ْ%1"},
  995. -- easy (end)
  996. {a="([^0-9])%-([^0-9])", b="%1%2"},
  997. {a="B", b="ـ"},
  998. }